- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces FineHM, a dataset of 9,979 short videos with multi-label harmful-content annotations and frame-level evidence boxes. ExplainHarm combines dynamic clue mining, temporal multimodal modeling, and clue-guided classification and grounding. It reports 78.5% classification accuracy, exceeding the strongest baseline in Table 3 by 11.3 percentage points, with component ablations supporting the design.
Critical strengths
-
Useful dataset and task formulation. Connecting co-occurring harmful labels to localized visual evidence supports more informative evaluation and human inspection than video-level classification alone.
-
Relevant component ablations. Removing dynamic clues reduces accuracy from 78.5% to 74.6%; removing local or global temporal modeling also lowers performance, providing initial evidence for their utility.
Critical weaknesses
-
The test protocol is unclear. Split counts and source-level grouping for clips and augmented variants are not specified. Section 5.1 also describes inference-time clue-bank updates and retrieval from annotated samples without defining retrieval-pool restrictions, label access, or reset policies. These omissions prevent a clear interpretation of the reported generalization, although they do not establish leakage.
-
Metrics and comparison conditions need clarification. Multi-label accuracy and grounding matching rules are undefined, and AR/mAP values are interchanged between Tables 3 and 4. Baseline adaptation and modality access are insufficiently documented. Additionally, box overlap measures localization agreement rather than whether the highlighted regions faithfully explain the classification. These issues weaken the empirical and explanatory claims.
Questions for authors
-
What are the split counts and source-grouping rules? Is annotated retrieval restricted to training data, and how is the clue bank updated and reset? A frozen-training-bank comparison would help clarify the effect of test-time updates.
-
Please define the classification and grounding metrics, reconcile AR/mAP across Tables 3/4/7, and specify baseline adaptation and modality access. Does Table 7 replace the clue module or compare standalone systems?
-
What independent annotation-quality checks were performed? Is explanation faithfulness evaluated, or should the claim be limited to localization aligned with human annotations?